Search papers, labs, and topics across Lattice.
Affiliation:
1
0
1
4
This work proposes Learning to Coach (L2C), a framework that trains a dedicated LLM-as-a-Coach to extract actionable experiential knowledge from an actor model's previous trajectory, and studies two such rewards: a same-instance reward, which improves subsequent responses on the original problem, and a cross-instance reward, which elicits knowledge that transfers to other instances.
